Probability Formulas

The rules of probability, the key counting formulas and the two distributions used most, the binomial and the normal, with a standard normal table computed by the Calxy statistics engine.

Basic probability rules

P(A) is always between 0 (impossible) and 1 (certain). For equally likely outcomes, P(A) = (number of favorable outcomes) ÷ (total number of outcomes).

Probability rules
RuleFormula
Basic probabilityP(A) = favorable outcomes ÷ total outcomes
ComplementP(not A) = 1 − P(A)
Addition (general)P(A or B) = P(A) + P(B) − P(A and B)
Addition (mutually exclusive)P(A or B) = P(A) + P(B)
Multiplication (general)P(A and B) = P(A) × P(B | A)
Multiplication (independent)P(A and B) = P(A) × P(B)
Conditional probabilityP(A | B) = P(A and B) ÷ P(B), P(B) > 0
Bayes' theoremP(A | B) = P(B | A) × P(A) ÷ P(B)
Total probabilityP(B) = P(B | A)P(A) + P(B | not A)P(not A)
PermutationsnPr = n! ÷ (n − r)!
CombinationsnCr = n! ÷ (r!(n − r)!)

Sources: OpenStax: Introductory Statistics 2e §3.1 Terminology; OpenStax: Introductory Statistics 2e §3.3 Two Basic Rules of Probability

Binomial distribution

For n independent trials, each succeeding with probability p, the number of successes X has P(X = k) = C(n, k) pᵏ (1 − p)ⁿ⁻ᵏ. Its mean is np and its variance np(1 − p).

Example: the probabilities of k heads in 10 fair coin tosses, computed exactly:

Binomial distribution, n = 10, p = 0.5
kC(10, k)P(X = k)
010.000977
1100.009766
2450.043945
31200.117188
42100.205078
52520.246094
62100.205078
71200.117188
8450.043945
9100.009766
1010.000977

Sources: NIST/SEMATECH: e-Handbook of Statistical Methods §1.3.6.6.18 Binomial Distribution

Normal distribution

The normal density with mean μ and standard deviation σ is f(x) = (1 ÷ (σ√(2π))) × e^(−(x − μ)² ÷ (2σ²)). Standardize with z = (x − μ) ÷ σ to use the standard normal (μ = 0, σ = 1).

About 68.27% of values lie within 1σ of the mean, 95.45% within 2σ and 99.73% within 3σ (the 68–95–99.7 rule).

Standard normal probabilities Φ(z) = P(Z ≤ z)
zΦ(z)P(−z ≤ Z ≤ z)P(Z > z)
00.50000.00000.5000
0.50.69150.38290.3085
10.84130.68270.1587
1.280.89970.79950.1003
1.6450.95000.90000.0500
1.960.97500.95000.0250
20.97720.95450.0228
2.3260.99000.98000.0100
2.5760.99500.99000.0050
30.99870.99730.0013

Sources: NIST/SEMATECH: e-Handbook of Statistical Methods §1.3.6.6.1 Normal Distribution; OpenStax: Introductory Statistics 2e §6.1 The Standard Normal Distribution

References

Frequently asked questions

What is the difference between independent and mutually exclusive events?

Independent events do not affect each other's probability, so P(A and B) = P(A)P(B). Mutually exclusive events cannot happen together, so P(A and B) = 0. Two events with nonzero probability cannot be both.

What does Bayes' theorem do?

It reverses a conditional probability: from P(B | A) it gives P(A | B). A typical use is finding the chance of a condition given a positive test from the test's accuracy and the condition's base rate.